Model Gallery
Discover and install AI models from our curated collection
Find Your Perfect Model
Filter by Model Type
Browse by Tags
step-3.7-flash
**[ModelPage]**: https://static.stepfun.com/blog/step-3.7-flash/
## 1. Introduction
Step 3.7 Flash is a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language model that combines a 196B-parameter language backbone with a 1.8B-parameter vision encoder for native image understanding. Engineered for high-frequency production workloads, it activates approximately 11B parameters per token and delivers a throughput of up to 400 tokens per second. Step 3.7 Flash supports a 256k context window and offers three selectable reasoning levels (low, medium, and high) so developers can easily balance speed, cost, and cognitive depth.
We built Step 3.7 Flash for developers who need to scale agentic workflows that combine perception, search, and reasoning. It is designed to handle intensive tasks such as parsing massive financial reports in one pass, running multi-step search loops with cross-source verification, or operating concurrent coding agents in high-throughput pipelines.
## 2. Capabilities & Performance
### Multimodal Perception and Verification
...
Repository: localaiLicense: apache-2.0
vits-piper-it_IT-paola-sherpa
Italian (it_IT) single-speaker Piper VITS voice "paola" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data, so it works for Italian out of the box.
Repository: localaiLicense: other
vits-piper-en_US-amy-sherpa
English (en_US) single-speaker Piper VITS voice "amy" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: other
vits-piper-es_ES-davefx-sherpa
Spanish (es_ES) single-speaker Piper VITS voice "davefx" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc0-1.0
vits-piper-fr_FR-siwis-sherpa
French (fr_FR) single-speaker Piper VITS voice "siwis" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc-by-4.0
vits-piper-de_DE-thorsten-sherpa
German (de_DE) single-speaker Piper VITS voice "thorsten" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc0-1.0
vits-piper-en_GB-alan-medium-sherpa
English (en_GB) single-speaker Piper VITS voice "alan" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: other
vits-piper-en_GB-alba-medium-sherpa
English (en_GB) single-speaker Piper VITS voice "alba" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc-by-4.0
vits-piper-en_GB-aru-medium-sherpa
English (en_GB) multi-speaker (12 voices) Piper VITS voice "aru" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data. Pick a speaker with the numeric voice/speaker id.
Repository: localaiLicense: cc-by-4.0
vits-piper-en_GB-cori-medium-sherpa
English (en_GB) single-speaker Piper VITS voice "cori" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc0-1.0
vits-piper-en_GB-jenny_dioco-medium-sherpa
English (en_GB) single-speaker Piper VITS voice "jenny_dioco" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: other
vits-piper-en_GB-northern_english_male-medium-sherpa
English (en_GB) single-speaker Piper VITS voice "northern_english_male" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc-by-sa-4.0
vits-piper-en_GB-semaine-medium-sherpa
English (en_GB) multi-speaker (4 voices) Piper VITS voice "semaine" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data. Pick a speaker with the numeric voice/speaker id. Non-commercial use only (CC BY-NC-SA 4.0).
Repository: localaiLicense: cc-by-nc-sa-4.0
vits-piper-en_GB-southern_english_female-medium-sherpa
English (en_GB) single-speaker Piper VITS voice "southern_english_female" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc-by-sa-4.0
vits-piper-en_GB-southern_english_male-medium-sherpa
English (en_GB) single-speaker Piper VITS voice "southern_english_male" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc-by-sa-4.0
vits-piper-en_GB-vctk-medium-sherpa
English (en_GB) multi-speaker (109 voices) Piper VITS voice "vctk" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data. Pick a speaker with the numeric voice/speaker id.
Repository: localaiLicense: cc-by-4.0
gpt-oss-20b
Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
We’re releasing two flavors of the open models:
gpt-oss-120b — for production, general purpose, high reasoning use cases that fits into a single H100 GPU (117B parameters with 5.1B active parameters)
gpt-oss-20b — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.
This model card is dedicated to the smaller gpt-oss-20b model. Check out gpt-oss-120b for the larger model.
Highlights
Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
Agentic capabilities: Use the models’ native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
Native MXFP4 quantization: The models are trained with native MXFP4 precision for the MoE layer, making gpt-oss-120b run on a single H100 GPU and the gpt-oss-20b model run within 16GB of memory.
Repository: localaiLicense: apache-2.0
gpt-oss-120b
Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
We’re releasing two flavors of the open models:
gpt-oss-120b — for production, general purpose, high reasoning use cases that fits into a single H100 GPU (117B parameters with 5.1B active parameters)
gpt-oss-20b — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.
This model card is dedicated to the smaller gpt-oss-20b model. Check out gpt-oss-120b for the larger model.
Highlights
Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
Agentic capabilities: Use the models’ native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
Native MXFP4 quantization: The models are trained with native MXFP4 precision for the MoE layer, making gpt-oss-120b run on a single H100 GPU and the gpt-oss-20b model run within 16GB of memory.
Repository: localaiLicense: apache-2.0
rfdetr-cpp-medium
RF-DETR Medium object detection model (DINOv2-small backbone, 576px input, 4 decoder layers), served
via the native rfdetr.cpp backend. Balanced detection quality vs. CPU latency — recommended when
Base is not accurate enough but Large is too slow. F16 quantization is the recommended default:
identical accuracy to F32, half the size. Drop-in for the /v1/detection endpoint.
Repository: localaiLicense: apache-2.0
rfdetr-cpp-seg-medium
RF-DETR Seg-Medium instance segmentation model (DINOv2-small backbone, 432px input, 5 decoder layers,
200 queries), served via the native rfdetr.cpp backend. Balanced segmentation quality vs. CPU latency
— recommended for everyday segmentation workloads. Returns both bounding boxes and per-instance masks
via the /v1/detection endpoint. F16 quantization is the recommended default.
Repository: localaiLicense: apache-2.0
impish_qwen_14b-1m
Supreme context One million tokens to play with.
Strong Roleplay internet RP format lovers will appriciate it, medium size paragraphs.
Qwen smarts built-in, but naughty and playful Maybe it's even too naughty.
VERY compliant with low censorship.
VERY high IFeval for a 14B RP model: 78.68.
Repository: localaiLicense: apache-2.0
Page
1
of many